API: upload document api (#1264)

### What problem does this PR solve?

API: Adds the feature of uploading document.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

sdk/python/ragflow/ragflow.py

@@ -13,9 +13,12 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 
-import os
-import requests
 import json
+import os
+
+import requests
+
+from api.settings import RetCode
 
 
 class RAGFlow:
@@ -23,10 +26,12 @@ class RAGFlow:
         '''
         api_url: http://<host_address>/api/v1
         dataset_url: http://<host_address>/api/v1/dataset
+        document_url: http://<host_address>/api/v1/documents
         '''
         self.user_key = user_key
         self.api_url = f"{base_url}/api/{version}"
         self.dataset_url = f"{self.api_url}/dataset"
+        self.document_url = f"{self.api_url}/documents"
         self.authorization_header = {"Authorization": "{}".format(self.user_key)}
 
     def create_dataset(self, dataset_name):
@@ -73,3 +78,54 @@ class RAGFlow:
         endpoint = f"{self.dataset_url}/{dataset_id}"
         response = requests.put(endpoint, json=params, headers=self.authorization_header)
         return response.json()
+
+# -------------------- content management -----------------------------------------------------
+
+    # ----------------------------upload local files-----------------------------------------------------
+    def upload_local_file(self, dataset_id, file_paths):
+        files = []
+
+        for file_path in file_paths:
+            if not isinstance(file_path, str):
+                return {'code': RetCode.ARGUMENT_ERROR, 'message': f"{file_path} is not string."}
+            if 'http' in file_path:
+                return {'code': RetCode.ARGUMENT_ERROR, 'message': "Remote files have not unsupported."}
+            if os.path.isfile(file_path):
+                files.append(('file', open(file_path, 'rb')))
+            else:
+                return {'code': RetCode.DATA_ERROR, 'message': f"The file {file_path} does not exist"}
+
+        res = requests.request('POST', url=f"{self.document_url}/{dataset_id}", files=files,
+                               headers=self.authorization_header)
+
+        result_dict = json.loads(res.text)
+        return result_dict
+
+    # ----------------------------upload remote files-----------------------------------------------------
+    # ----------------------------download a file-----------------------------------------------------
+
+    # ----------------------------delete a file-----------------------------------------------------
+
+    # ----------------------------enable rename-----------------------------------------------------
+
+    # ----------------------------list files-----------------------------------------------------
+
+    # ----------------------------start parsing-----------------------------------------------------
+
+    # ----------------------------stop parsing-----------------------------------------------------
+
+    # ----------------------------show the status of the file-----------------------------------------------------
+
+    # ----------------------------list the chunks of the file-----------------------------------------------------
+
+    # ----------------------------delete the chunk-----------------------------------------------------
+
+    # ----------------------------edit the status of the chunk-----------------------------------------------------
+
+    # ----------------------------insert a new chunk-----------------------------------------------------
+
+    # ----------------------------upload a file-----------------------------------------------------
+
+    # ----------------------------get a specific chunk-----------------------------------------------------
+
+    # ----------------------------retrieval test-----------------------------------------------------

sdk/python/test/test_data/.txt

@@ -0,0 +1,2 @@
+hhh
+hhh

sdk/python/test/test_data/test.txt

@@ -0,0 +1,3 @@
+test
+test
+test

sdk/python/test/test_data/test1.txt

@@ -0,0 +1,2 @@
+test1
+test1

sdk/python/test/test_document.py

@@ -0,0 +1,180 @@
+from api.settings import RetCode
+from test_sdkbase import TestSdk
+from ragflow import RAGFlow
+import pytest
+from common import API_KEY, HOST_ADDRESS
+from api.contants import NAME_LENGTH_LIMIT
+
+
+class TestFile(TestSdk):
+    """
+    This class contains a suite of tests for the content management functionality within the dataset.
+    It ensures that the following functionalities as expected:
+        1. upload local files
+        2. upload remote files
+        3. download a file
+        4. delete a file
+        5. enable rename
+        6. list files
+        7. start parsing
+        8. end parsing
+        9. check the status of the file
+        10. list the chunks
+        11. delete a chunk
+        12. insert a new chunk
+        13. edit the status of chunk
+        14. get the specific chunk
+        15. retrieval test
+    """
+
+# ----------------------------upload local files-----------------------------------------------------
+    def test_upload_two_files(self):
+        """
+        Test uploading two files with success.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_two_files")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ["test_data/test.txt", "test_data/test1.txt"]
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert res['code'] == RetCode.SUCCESS and res['data'] is True and res['message'] == 'success'
+
+    def test_upload_one_file(self):
+        """
+        Test uploading one file with success.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_one_file")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ["test_data/test.txt"]
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert res['code'] == RetCode.SUCCESS and res['data'] is True and res['message'] == 'success'
+
+    def test_upload_nonexistent_files(self):
+        """
+        Test uploading a file which does not exist.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_nonexistent_files")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ["test_data/imagination.txt"]
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert res['code'] == RetCode.DATA_ERROR and "does not exist" in res['message']
+
+    def test_upload_file_if_dataset_does_not_exist(self):
+        """
+        Test uploading files if the dataset id does not exist.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        file_paths = ["test_data/test.txt"]
+        res = ragflow.upload_local_file("111", file_paths)
+        assert res['code'] == RetCode.DATA_ERROR and res['message'] == "Can't find this dataset"
+
+    def test_upload_file_without_name(self):
+        """
+        Test uploading files that do not have name.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_file_without_name")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ["test_data/.txt"]
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert res['code'] == RetCode.SUCCESS
+
+    def test_upload_file_without_name1(self):
+        """
+        Test uploading files that do not have name.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_file_without_name")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ["test_data/.txt", "test_data/empty.txt"]
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert res['code'] == RetCode.SUCCESS
+
+    def test_upload_files_exceeding_the_number_limit(self):
+        """
+        Test uploading files whose number exceeds the limit.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_files_exceeding_the_number_limit")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ["test_data/test.txt", "test_data/test1.txt"] * 256
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert (res['message'] ==
+                'You try to upload 512 files, which exceeds the maximum number of uploading files: 256'
+                and res['code'] == RetCode.DATA_ERROR)
+
+    def test_upload_files_without_files(self):
+        """
+        Test uploading files without files.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_files_without_files")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = [None]
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert (res['message'] == 'None is not string.' and res['code'] == RetCode.ARGUMENT_ERROR)
+
+    def test_upload_files_with_two_files_with_same_name(self):
+        """
+        Test uploading files with the same name.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_files_with_two_files_with_same_name")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ['test_data/test.txt'] * 2
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert (res['message'] == 'success' and res['code'] == RetCode.SUCCESS)
+
+    def test_upload_files_with_file_paths(self):
+        """
+        Test uploading files with only specifying the file path's repo.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_files_with_file_paths")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ['test_data/']
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert (res['message'] == 'The file test_data/ does not exist' and res['code'] == RetCode.DATA_ERROR)
+
+    def test_upload_files_with_remote_file_path(self):
+        """
+        Test uploading files with remote files.
+        """
+        ragflow = RAGFlow(API_KEY, HOST_ADDRESS)
+        created_res = ragflow.create_dataset("test_upload_files_with_remote_file_path")
+        dataset_id = created_res['data']['dataset_id']
+        file_paths = ['https://github.com/genostack/ragflow']
+        res = ragflow.upload_local_file(dataset_id, file_paths)
+        assert res['code'] == RetCode.ARGUMENT_ERROR and res['message'] == 'Remote files have not unsupported.'
+
+# ----------------------------upload remote files-----------------------------------------------------
+
+# ----------------------------download a file-----------------------------------------------------
+
+# ----------------------------delete a file-----------------------------------------------------
+
+# ----------------------------enable rename-----------------------------------------------------
+
+# ----------------------------list files-----------------------------------------------------
+
+# ----------------------------start parsing-----------------------------------------------------
+
+# ----------------------------stop parsing-----------------------------------------------------
+
+# ----------------------------show the status of the file-----------------------------------------------------
+
+# ----------------------------list the chunks of the file-----------------------------------------------------
+
+# ----------------------------delete the chunk-----------------------------------------------------
+
+# ----------------------------edit the status of the chunk-----------------------------------------------------
+
+# ----------------------------insert a new chunk-----------------------------------------------------
+
+# ----------------------------upload a file-----------------------------------------------------
+
+# ----------------------------get a specific chunk-----------------------------------------------------
+
+# ----------------------------retrieval test-----------------------------------------------------